© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13485
    Prev
    Next
    INDEX
    Explanations

    words with the letters 'bri', 'gri', 'dru', 'sci', 'fri', 'ri' or 'to' followed by a number

    oai_token-act-pair · gemini-2.0-flash

    Bri/Gri/Fri

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hermosa
    -0.47
    tapa
    -0.46
    Tē
    -0.45
     typedef
    -0.44
     tow
    -0.44
    ərbaycan
    -0.44
     hab
    -0.44
    tu
    -0.44
     UIAlert
    -0.43
    verbosity
    -0.43
    POSITIVE LOGITS
    ReusableCell
    0.58
    mless
    0.57
     ferons
    0.54
     betweenstory
    0.54
    bbons
    0.54
     فريبيس
    0.54
    colates
    0.53
    jzen
    0.53
    bber
    0.53
    zzlies
    0.51
    Activations Density 3.305%

    No Known Activations